Skip to main content
SpringerLink
Log in

On Label Granularity and Object Localization

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13670))

Included in the following conference series:

Abstract

Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/visipedia/inat_loc/.

References

  1. iNaturalist. www.inaturalist.org. Accessed 7 Mar 2022

  2. Bae, W., Noh, J., Kim, G.: Rethinking class activation mapping for weakly supervised object localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 618–634. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_37

    Chapter  Google Scholar 

  3. Benenson, R., Popov, S., Ferrari, V.: Large-scale interactive object segmentation with human annotators. In: CVPR (2019)

    Google Scholar 

  4. Beyer, L., Hénaff, O.J., Kolesnikov, A., Zhai, X., van den Oord, A.: Are we done with ImageNet? arXiv:2006.07159 (2020)

  5. Bilal, A., Jourabloo, A., Ye, M., Liu, X., Ren, L.: Do convolutional neural networks learn class hierarchy? IEEE Trans. Visual Comput. Graphics 24(1), 152–162 (2017)

    Article  Google Scholar 

  6. Bilen, H., Pedersoli, M., Tuytelaars, T.: Weakly supervised object detection with convex clustering. In: CVPR (2015)

    Google Scholar 

  7. Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: CVPR (2016)

    Google Scholar 

  8. Borenstein, E., Ullman, S.: Class-specific, top-down segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109–122. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-47967-8_8

    Chapter  Google Scholar 

  9. Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)

    Google Scholar 

  10. Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. In: WACV (2018)

    Google Scholar 

  11. Choe, J., Oh, S.J., Chun, S., Akata, Z., Shim, H.: Evaluation for weakly supervised object localization: protocol, metrics, and datasets. arXiv:2007.04178 (2020)

  12. Choe, J., Oh, S.J., Lee, S., Chun, S., Akata, Z., Shim, H.: Evaluating weakly supervised object localization methods right. In: CVPR (2020)

    Google Scholar 

  13. Choe, J., Shim, H.: Attention-based dropout layer for weakly supervised object localization. In: CVPR (2019)

    Google Scholar 

  14. Choi, Y., et al.: EdNet: a large-scale hierarchical dataset in education. In: Bittencourt, I.I., Cukurova, M., Muldner, K., Luckin, R., Millán, E. (eds.) AIED 2020. LNCS (LNAI), vol. 12164, pp. 69–73. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52240-7_13

    Chapter  Google Scholar 

  15. Cole, E., Yang, X., Wilber, K., Mac Aodha, O., Belongie, S.: When does contrastive visual representation learning work? In: CVPR (2022)

    Google Scholar 

  16. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)

    Google Scholar 

  17. Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88, 303–338 (2010)

    Article  Google Scholar 

  18. Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)

    Google Scholar 

  19. Galleguillos, C., Babenko, B., Rabinovich, A., Belongie, S.: Weakly supervised object localization with stable segmentations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 193–207. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_16

    Chapter  Google Scholar 

  20. van Gemert, J.C., Verschoor, C.R., Mettes, P., Epema, K., Koh, L.P., Wich, S.: Nature conservation drones for automatic localization and counting of animals. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 255–270. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16178-5_17

    Chapter  Google Scholar 

  21. Gokberk Cinbis, R., Verbeek, J., Schmid, C.: Multi-fold mil training for weakly supervised object localization. In: CVPR (2014)

    Google Scholar 

  22. Guo, S., et al.: The iMaterialist fashion attribute dataset. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, p. 0 (2019)

    Google Scholar 

  23. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)

    Google Scholar 

  24. Jung, H., Oh, Y.: Towards better explanations of class activation mapping. In: ICCV (2021)

    Google Scholar 

  25. Khan, M.H., et al.: AnimalWeb: a large-scale hierarchical dataset of annotated animal faces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6939–6948 (2020)

    Google Scholar 

  26. Ki, M., Uh, Y., Lee, W., Byun, H.: In-sample contrastive learning and consistent attention for weakly supervised object localization. In: ACCV (2020)

    Google Scholar 

  27. Kim, J.M., Choe, J., Akata, Z., Oh, S.J.: Keep calm and improve visual feature attribution. In: ICCV (2021)

    Google Scholar 

  28. Kim, J., Choe, J., Yun, S., Kwak, N.: Normalization matters in weakly supervised object localization. In: ICCV (2021)

    Google Scholar 

  29. Kuznetsova, A., et al.: The open images dataset V4. IJCV 128, 1956–1981 (2020)

    Article  Google Scholar 

  30. Li, Z., Dong, M., Wen, S., Hu, X., Zhou, P., Zeng, Z.: CLU-CNNs: object detection for medical images. Neurocomputing 350, 53–59 (2019)

    Article  Google Scholar 

  31. Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. Technical report (2013)

    Google Scholar 

  32. Nguyen, M.H., Torresani, L., De La Torre, F., Rother, C.: Weakly supervised discriminative localization and classification: a joint learning process. In: ICCV (2009)

    Google Scholar 

  33. Oh, S.J., Benenson, R., Khoreva, A., Akata, Z., Fritz, M., Schiele, B.: Exploiting saliency for object segmentation from image level labels. In: CVPR (2017)

    Google Scholar 

  34. Opelt, A., Pinz, A.: Object localization with boosting and weak supervision for generic object recognition. In: Kalviainen, H., Parkkinen, J., Kaarna, A. (eds.) SCIA 2005. LNCS, vol. 3540, pp. 862–871. Springer, Heidelberg (2005). https://doi.org/10.1007/11499145_87

    Chapter  Google Scholar 

  35. Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Is object localization for free?-Weakly-supervised learning with convolutional neural networks. In: CVPR (2015)

    Google Scholar 

  36. Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based models. In: ICCV (2011)

    Google Scholar 

  37. Papadopoulos, D.P., Uijlings, J.R., Keller, F., Ferrari, V.: Extreme clicking for efficient object annotation. In: ICCV (2017)

    Google Scholar 

  38. Peng, X., Wang, K., Zhu, Z., Wang, M., You, Y.: Crafting better contrastive views for Siamese representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16031–16040 (2022)

    Google Scholar 

  39. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)

    Google Scholar 

  40. Robinson, J., Jegelka, S., Sra, S.: Strength from weakness: fast learning using weak supervision. In: ICML (2020)

    Google Scholar 

  41. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115, 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  42. Sariyildiz, M.B., Kalantidis, Y., Larlus, D., Alahari, K.: Concept generalization in visual representation learning. In: ICCV (2021)

    Google Scholar 

  43. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)

    Google Scholar 

  44. Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616–2625 (2020)

    Google Scholar 

  45. Singh, K.K., Lee, Y.J.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: ICCV (2017)

    Google Scholar 

  46. Taherkhani, F., Kazemi, H., Dabouei, A., Dawson, J., Nasrabadi, N.M.: A weakly supervised fine label classifier enhanced by coarse supervision. In: ICCV (2019)

    Google Scholar 

  47. Tang, P., Wang, X., Bai, X., Liu, W.: Multiple instance detection network with online instance classifier refinement. In: CVPR (2017)

    Google Scholar 

  48. Touvron, H., Sablayrolles, A., Douze, M., Cord, M., Jégou, H.: Grafit: learning fine-grained image representations with coarse labels. In: ICCV (2021)

    Google Scholar 

  49. Uijlings, J., Popov, S., Ferrari, V.: Revisiting knowledge transfer for training object class detectors. In: CVPR (2018)

    Google Scholar 

  50. Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR (2021)

    Google Scholar 

  51. Van Horn, G., et al.: The iNaturalist species classification and detection dataset. In: CVPR (2018)

    Google Scholar 

  52. Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report, CNS-TR-2011-001. California Institute of Technology (2011)

    Google Scholar 

  53. Wang, R., Mahajan, D., Ramanathan, V.: What leads to generalization of object proposals? In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 464–478. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66096-3_32

    Chapter  Google Scholar 

  54. Wei, X.S., et al.: Fine-grained image analysis with deep learning: a survey. PAMI PP, 1 (2021)

    Google Scholar 

  55. Wu, B., Iandola, F., Jin, P.H., Keutzer, K.: SqueezeDet: unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving. In: CVPR Workshops (2017)

    Google Scholar 

  56. Xu, Y., Qian, Q., Li, H., Jin, R., Hu, J.: Weakly supervised representation learning with coarse labels. In: ICCV (2021)

    Google Scholar 

  57. Yang, H., Wu, H., Chen, H.: Detecting 11K classes: large scale object detection without fine-grained bounding boxes. In: ICCV (2019)

    Google Scholar 

  58. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)

    Google Scholar 

  59. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53

    Chapter  Google Scholar 

  60. Zhang, D., Han, J., Cheng, G., Yang, M.H.: Weakly supervised object localization and detection: a survey. PAMI 44, 5866–5885 (2021)

    Google Scholar 

  61. Zhang, X., Wei, Y., Feng, J., Yang, Y., Huang, T.S.: Adversarial complementary learning for weakly supervised object localization. In: CVPR (2018)

    Google Scholar 

  62. Zhang, X., Wei, Y., Kang, G., Yang, Y., Huang, T.: Self-produced guidance for weakly-supervised object localization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 610–625. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_37

    Chapter  Google Scholar 

  63. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)

    Google Scholar 

Download references

Acknowledgements

We thank the iNaturalist community for sharing images and species annotations. This work was supported by the Caltech Resnick Sustainability Institute, an NSF Graduate Research Fellowship (grant number DGE1745301), and the Pioneer Centre for AI (DNRF grant number P1).

Author information

Authors and Affiliations

  1. Caltech, Pasadena, USA

    Elijah Cole & Pietro Perona

  2. Google, Mountain View, USA

    Kimberly Wilber, Xuan Yang, Marco Fornoni & Andrew Howard

  3. Cornell University, Ithaca, USA

    Grant Van Horn

  4. University of Copenhagen, Copenhagen, Denmark

    Serge Belongie

  5. University of Edinburgh, Edinburgh, UK

    Oisin Mac Aodha

Authors
  1. Elijah Cole
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kimberly Wilber
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Grant Van Horn
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xuan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marco Fornoni
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Pietro Perona
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Serge Belongie
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Andrew Howard
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Oisin Mac Aodha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Elijah Cole .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 7076 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cole, E. et al. (2022). On Label Granularity and Object Localization. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13670. Springer, Cham. https://doi.org/10.1007/978-3-031-20080-9_35

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20080-9_35

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20079-3

  • Online ISBN: 978-3-031-20080-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation